{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T03:41:42Z","timestamp":1767152502432,"version":"3.48.0"},"reference-count":29,"publisher":"World Scientific Pub Co Pte Ltd","issue":"04","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Semantic Computing"],"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:p>While large language models exhibit broad capabilities, they often require supplementation for optimal performance on domain-specific tasks. To address this, we built TriRAG, an innovative enhancement to traditional Retrieval-Augmented Generation. This paper presents an extended version of our earlier TriRAG work. TriRAG integrates a structured knowledge graph composed of semantic triples derived from text, significantly improving the performance of LLMs on multiple-choice question-answering tasks. Our method dynamically converts relevant text into triples, embeds them into vectors, and retrieves the most useful triples for a given question by calculating vector similarities. By having the triple-based approach instead of the conventional text-based retrieval approach, TriRAG enables more precise and efficient information retrieval. This directly enhances the accuracy of LLM-generated responses in multiple-choice question-answering tasks. We evaluate TriRAG using the Textbook Question Answering dataset, demonstrating consistent improvements over traditional RAG methods across leading LLMs, including Gemma, Llama, and ChatGPT variants. Experimental results and ablation studies confirm that our triple-based system enhances both retrieval accuracy and processing efficiency, leading to better overall model performance.<\/jats:p>","DOI":"10.1142\/s1793351x25450023","type":"journal-article","created":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:00:39Z","timestamp":1760162439000},"page":"547-567","source":"Crossref","is-referenced-by-count":0,"title":["Extending TriRAG for Advancing Retrieval-Augmented Generation Method with Triple-Based Knowledge Graphs for Improved Question Answering"],"prefix":"10.1142","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8772-6254","authenticated-orcid":false,"given":"Hongzhi","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Information Technology, Carleton University, Ottawa, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1859-8296","authenticated-orcid":false,"given":"M. Omair","family":"Shafiq","sequence":"additional","affiliation":[{"name":"School of Information Technology, Carleton University, Ottawa, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"S1793351X25450023BIB001","unstructured":"OpenAI, ChatGPT, Version 4, 2023, Available at https:\/\/openai.com\/chatgpt."},{"key":"S1793351X25450023BIB002","unstructured":"H. Touvron, L. Martin, K. Stone, P. Albert, A. Almahairi, Y. Babaei, N. Bashlykov, S. Batra, P. Bhargava, S. Bhosale and D. Bikel, Llama 2: Open foundation and fine-tuned chat models, preprint (2023), arXiv:2307.09288."},{"key":"S1793351X25450023BIB003","unstructured":"R. Anil, A. M. Dai, O. Firat, M. Johnson, D. Lepikhin, A. Passos, S. Shakeri, E. Taropa, P. Bailey, Z. Chen and E. Chu, Palm 2 technical report, preprint (2023), arXiv:2305.10403."},{"key":"S1793351X25450023BIB004","unstructured":"G. Team, R. Anil, S. Borgeaud, Y. Wu, J. B. Alayrac, J. Yu, R. Soricut, J. Schalkwyk, A. M. Dai, A. Hauth and K. Millican, Gemini: A family of highly capable multimodal models, preprint (2023), arXiv:2312.11805."},{"key":"S1793351X25450023BIB005","first-page":"9459","volume":"33","author":"Lewis P.","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"S1793351X25450023BIB006","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.389"},{"key":"S1793351X25450023BIB007","doi-asserted-by":"crossref","unstructured":"F. Remy, K. Demuynck and T. Demeester, BioLORD-2023: Semantic textual representations fusing LLM and clinical knowledge graph insights, preprint (2023), arXiv:2311.16075.","DOI":"10.1093\/jamia\/ocae029"},{"key":"S1793351X25450023BIB008","unstructured":"L. Zhang, K. Jijo, S. Setty, E. Chung, F. Javid, N. Vidra and T. Clifford, Enhancing large language model performance to answer questions and extract information more accurately, preprint (2024), arXiv:2402.01722."},{"key":"S1793351X25450023BIB009","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111332"},{"volume-title":"ICML\u201924 Workshop ML for Life and Material Science: From Theory to Industry Applications","year":"2024","author":"Delile J.","key":"S1793351X25450023BIB010"},{"key":"S1793351X25450023BIB011","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00530"},{"key":"S1793351X25450023BIB012","unstructured":"J. Boylan, S. Mangla, D. Thorn, D. G. Ghalandari, P. Ghaffari and C. Hokamp, KGValidator: A framework for automatic validation of knowledge graph construction, preprint (2024), arXiv:2404.15923."},{"key":"S1793351X25450023BIB013","unstructured":"C. S. Krishna, Prompt generate train (PGT): Few-shot domain adaption of retrieval augmented generation models for open book question-answering, preprint (2023), arXiv:2307.05915."},{"key":"S1793351X25450023BIB014","unstructured":"Y. Zhu, C. Ren, S. Xie, S. Liu, H. Ji, Z. Wang, T. Sun, L. He, Z. Li, X. Zhu and C. Pan, REALM: RAG-driven enhancement of multimodal electronic health records analysis via large language models, preprint (2024), arXiv:2402.07016."},{"key":"S1793351X25450023BIB015","unstructured":"H. Chen, R. Xie, X. Cui, Z. Yan, X. Wang, Z. Xuan and K. Zhang, LKPNR: LLM and KG for personalized news recommendation framework, preprint (2023), arXiv:2308.12028."},{"key":"S1793351X25450023BIB016","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1023"},{"key":"S1793351X25450023BIB017","first-page":"143","volume-title":"Asian Conf. Machine Learning","author":"Shu D.","year":"2025"},{"key":"S1793351X25450023BIB018","unstructured":"OpenAI, text-embedding-ada-002, Available at https:\/\/platform.openai.com\/docs\/ guides\/embeddings."},{"key":"S1793351X25450023BIB019","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.571"},{"key":"S1793351X25450023BIB020","unstructured":"G. Team, T. Mesnard, C. Hardin, R. Dadashi, S. Bhupatiraju, S. Pathak, L. Sifre, M. Rivi\u00e9re, M. S. Kale, J. Love and P. Tafti, Gemma: Open models based on gemini research and technology, preprint (2024), arXiv:2403.08295."},{"key":"S1793351X25450023BIB021","unstructured":"H. Touvron, L. Martin, K. Stone, P. Albert, A. Almahairi, Y. Babaei, N. Bashlykov, S. Batra, P. Bhargava, S. Bhosale and D. Bikel, Llama 2: Open foundation and fine-tuned chat models, preprint (2023), arXiv:2307.09288."},{"key":"S1793351X25450023BIB022","unstructured":"A. Dubey, A. Jauhri, A. Pandey, A. Kadian, A. Al-Dahle, A. Letman, A. Mathur, A. Schelten, A. Yang, A. Fan and A. Goyal, The Llama 3 herd of models, preprint (2024), arXiv:2407.21783."},{"key":"S1793351X25450023BIB023","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3180563"},{"key":"S1793351X25450023BIB024","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3231463"},{"key":"S1793351X25450023BIB025","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-53308-2_8"},{"key":"S1793351X25450023BIB026","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109441"},{"key":"S1793351X25450023BIB027","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"S1793351X25450023BIB028","unstructured":"J. Huber and A. Troynikov, Chroma (2023), Available at https:\/\/github.com\/chroma-core\/chroma."},{"key":"S1793351X25450023BIB029","doi-asserted-by":"publisher","DOI":"10.1109\/ICSC64641.2025.00011"}],"container-title":["International Journal of Semantic Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S1793351X25450023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T03:36:57Z","timestamp":1767152217000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S1793351X25450023"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":29,"journal-issue":{"issue":"04","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["10.1142\/S1793351X25450023"],"URL":"https:\/\/doi.org\/10.1142\/s1793351x25450023","relation":{},"ISSN":["1793-351X","1793-7108"],"issn-type":[{"type":"print","value":"1793-351X"},{"type":"electronic","value":"1793-7108"}],"subject":[],"published":{"date-parts":[[2025,10,27]]}}}